AMALGAM: A Matching Approach to fairfy tabuLar data with knowledGe grAph Model

TL;DR

AMALGAM is a novel matching method that leverages knowledge graphs to efficiently annotate tabular data, improving the process of linking data to background knowledge for semantic applications.

Contribution

It introduces a combined lookup and filtering approach with text preprocessing for fast, knowledge-based tabular data annotation, validated on Semantic Web Challenge tasks.

Findings

Promising results in entity annotation tasks

Effective combination of lookup, filtering, and text processing

Validated on Semantic Web Challenge datasets

Abstract

In this paper we present AMALGAM, a matching approach to fairify tabular data with the use of a knowledge graph. The ultimate goal is to provide fast and efficient approach to annotate tabular data with entities from a background knowledge. The approach combines lookup and filtering services combined with text pre-processing techniques. Experiments conducted in the context of the 2020 Semantic Web Challenge on Tabular Data to Knowledge Graph Matching with both Column Type Annotation and Cell Type Annotation tasks showed promising results.